© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100875
    Prev
    Next
    INDEX
    Explanations

    Twelve followed by a group

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron specifically detects the spelled-out number “Twelve.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dando
    -2.92
     enorme
    -2.84
    臜
    -2.80
    ↵↵
    -2.70
    凄い
    -2.66
    0
    -2.63
    亖
    -2.58
     notre
    -2.58
    シャレ
    -2.53
    S
    -2.48
    POSITIVE LOGITS
    There
    3.91
    This
    3.89
    With
    3.73
    It
    3.73
    If
    3.63
    When
    3.63
    there
    3.58
    These
    3.47
    During
    3.41
    Every
    3.31
    Activations Density 0.004%

    No Known Activations